INDEX

Explanations

instructions related to a task or process

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Carav

-0.41

 وز

-0.40

如今

-0.40

EMBLE

-0.39

 איז

-0.38

 Portanto

-0.38

 hiệu

-0.38

哪

-0.38

 tert

-0.38

-0.37

POSITIVE LOGITS

FilterChain

0.79

principalColumn

0.79

 >=",

0.73

 GenerationType

0.69

]")]

0.68

 <=",

0.67

 IBOutlet

0.63

êques

0.63

MigrationBuilder

0.62

 Jérusalem

0.62

Activations Density 0.279%

instructions related to a task or process

No Comments

No Known Activations